Things included in this PR: - Pi support. - Auto-resume when limits reset - T3 Code MCP (create, launch, message, wait on, read, search and interrupt threads) - `delegate_task` lets an agent start child agents on any provider or model - ACP Registry: add any registry agent (Devin, Cline, Kimi, Droid, and more) - Cursor runs on the official Cursor SDK, not the (broken) CLI - OpenCode 2 support - Agents can rename threads, regenerate titles, link PRs and settle threads - New MCP tools for worktree handoff, and for listing and closing previews - Proper server-side queueing and steering - Thread forking - Switch provider or model in the middle of a thread - Native subagents show as child threads in a lineage view, with their model, status and history - Use `@` with a thread name, or drag a thread from the sidebar, to attach it as context - Scheduled tasks - Tons more I'm forgetting Pumped this landed. We'll have a lot of cleanup to do to get it perfect, so expect lots of updates throughout the next few days :)

Also another issue is a lot of these "open-sourced' jev models are just running some LoRa/distilled/fine-tuned variant of QWEN which from a cost perspective makes no sense when at that point youre better off hosting QWEN

A lot of hype on jev-fying models. However based on some evals ive been runing, it seems these models never perform better than the existing classifiers out there already and are generally way more expensive to host at scale for what is a delta of +- 10% precision boost :/

I’m afraid to tell you that it is effectively impossible to do the kind of writing I used to do on this website, not because anyone at OpenAI censors me but because of the sheer volume of hostility I get for sharing my analysis as a frontier lab employee. I enjoyed writing quick takes on this website for one basic reason: I could get rapid feedback on my own ideation process in real time. Post the early version of the take here, see the criticism; then refine, sharpen, and repeat. Unfortunately now that feature of this site is gone, because the feedback I get is now almost exclusively colored by resentment at the fact that I work at a frontier lab or other forms of hatred for my employer. The feedback signal is essentially useless now, so writing on here is not fruitful for me anymore. Literally everything I write now is responded to with “of course you said that because .” I am truly just writing what I think and would have written anyway, but everyone reads what I say in the shrieking tone of “this is what openai thinks!!!!” (to be clear, my posts are not what openai thinks). This is an unpleasant and more importantly unproductive pattern for me. I anticipate that the shape of this account will change significantly as a result. I do not currently know how. It will not become a LinkedIn feed. It will change in some other way. It will no longer be a real-time accounting of my own thinking as it develops, since this is precisely the thing that seems impossible to do now. That will have to shift to private channels.

New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.

New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.

The US government is going to destroy the American AI industry. OpenAI just confirmed that GPT 5.6 will release in a limited preview to a small group of partners. The government is approving access customer by customer. Anthropic got hit harder. Fable 5 and Mythos were suspended entirely two weeks ago. Two government interventions in the same month. Meanwhile China ships GLM 5.2, Kimi K2.7, and Qwen 3.7 as open weights to anyone with a download link. The US is gating its best AI. China is giving it away. We are losing this race in slow motion. This needs to change.

New w/ @leomschwartz @amir: The Trump admin has asked OpenAI to stagger the release of GPT-5.6 over security concerns. On Thursday, CEO Sam Altman told staff that the government will be approving access to GPT-5.6 customer by customer, a highly unusual approach.

Bro, the thing that keeps me up at night isn't losing my job to AI. It's that I actually believed the whole "get really good and you'll be fine" advice. So I did. Spent years coding. Built random side projects nobody used. Contributed to open source. Read docs for fun. Got roasted in code reviews. Slowly got better. And now the market just doesn't care as much as it used to. Not because the work wasn't worth it. Just because a lot of what used to make people valuable can now be generated on demand. That's the part that messes with my head.